© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118862
    Prev
    Next
    INDEX
    Explanations

    more efficient or easier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ra
    -0.06
     naast
    -0.06
     donc
    -0.05
     na
    -0.05
     تحتاج
    -0.05
     multa
    -0.05
     وہ
    -0.05
     domin
    -0.05
     control
    -0.05
     இருப்பதால்
    -0.05
    POSITIVE LOGITS
     our
    0.07
    感じで
    0.07
     nuestros
    0.07
    Would
    0.07
    我们的
    0.06
     Would
    0.06
    我們的
    0.06
     nuestro
    0.06
    runde
    0.06
    would
    0.06
    Activations Density 0.021%

    No Known Activations